Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems

DOI10.1007/s10994-020-05939-8OpenAlexW3137303899MaRDI QIDQ2071401

Alberto Maria Metelli, Matteo Giuliani, Marcello Restelli, Amarildo Likmeta, Andrea Tirinzoni, Giorgia Ramponi

Publication date: 28 January 2022

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10994-020-05939-8

zbMATH Keywords

inverse reinforcement learningIRL for real lifemodel-free IRLmultiple experts IRLnon-stationary IRLtruly batch IRL

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (1)

Model-free inverse reinforcement learning with multi-intention, unlabeled, and overlapping demonstrations

Uses Software

• SUMO
• CARLA

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A well-conditioned estimator for large-dimensional covariance matrices
• Policy search for motor primitives in robotics
• Multi-robot inverse reinforcement learning under occlusion with estimation of state transitions
• Simple statistical gradient-following algorithms for connectionist reinforcement learning
• On a routing problem
• Deep hedging

This page was built for publication: Dealing with multiple experts and non-stationarity in inverse reinforcement learning: an application to real-life problems